UBTree: Parallel Tree Drafting via Unigram and Bigram Models for Speculative Decoding
cs.CL
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- Program Synthesis with Large Language Models
- Accelerating Large Language Model Decoding with Speculative Sampling
- Evaluating Large Language Models Trained on Code
- DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
- Training Verifiers to Solve Math Word Problems
- Trace Length is a Simple Uncertainty Signal in Reasoning Models
- DiffusionGemma Technical Report
- Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
- Mercury: Ultra-Fast Language Models Based on Diffusion
- Kimi Linear: An Expressive, Efficient Attention Architecture
- SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
- DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees
- WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference
- DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference
- Accelerating Speculative Decoding with Block Diffusion Draft Trees
- Bole: Efficient Tree Speculation for Hybrid-Attention Language Models
- Dream-Coder 7B: An Open Diffusion Language Model for Code
- The Perfect Blend: Redefining RLHF with Mixture of Judges
- Qwen3 Technical Report
- The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering